Modeling semantic concepts in an embedding space as distributions
US11238362B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jan 15, 2016 |
| Grant date | Feb 1, 2022 |
| Priority date | — |
| Expiry date | Dec 4, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/09
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Modeling semantic concepts in an embedding space as distributions is described. In the embedding space, both images and text labels are represented. The text labels describe semantic concepts that are exhibited in image content. In the embedding space, the semantic concepts described by the text labels are modeled as distributions. By using distributions, each semantic concept is modeled as a continuous cluster which can overlap other clusters that model other semantic concepts. For example, a distribution for the semantic concept “apple” can overlap distributions for the semantic concepts “fruit” and “tree” since can refer to both a fruit and a tree. In contrast to using distributions, conventionally configured visual-semantic embedding spaces represent a semantic concept as a single point. Thus, unlike these conventionally configured embedding spaces, the embedding spaces described herein are generated to model semantic concepts as distributions, such as Gaussian distributions, Gaussian mixtures, and so on.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.